Responding to Online Reviews in Competitive Markets: A Controlled Diffusion Approach

2023 | Management Information Systems Quarterly | Citations: 0

Authors: Yang, Mingwen; Zheng, Zhiqiang (Eric); Mookerjee, Vijay; Chen, Hongyu

Abstract: We study how firms respond to online customer reviews in a competitive market w ... Expand

Abstract: We study how firms respond to online customer reviews in a competitive market where they jostle with one another for sales based on online ratings. The focus of this paper is on how firms can optimally manage their ratings through management response and how review ratings affect the sales and profits of competing firms. We develop a controlled diffusion process to model the coevolution of sales and ratings as a function of the response strategy chosen to maximize profit over time. Our model considers a variety of factors, such as profit margin and customer rating sensitivity, that influence a firm's effort to manage ratings and subsequently its sales and profits. More response effort needs to be exerted to manage ratings when either the profit margin of a tour is very high or customers are very sensitive to ratings. We estimate our model using data on Ctrip's tours that include each tour's sales, reviews, prices, and tour features. We find that consumers anchor their beliefs in the mean market rating and that their purchase decisions depend on the tour's rating relative to this anchor. Thus, relative, rather than absolute, ratings matter. Our study informs firms on how competition and other primitives impact their efforts to manage ratings and hence profit. Our methodology allowed us to conduct "what-if" analyses, for example, to study what would happen to the review ratings, sales, and profits of a tour if a firm adopted a different response strategy. We were also able to provide turnaround strategies for struggling tours, i.e., factors that a loss-making tour should change if it wishes to make a positive profit. Ultimately, we conducted a competitive analysis that allowed us to modify certain parameters that affect the intensity of competition and hence the sales and the profits of competing tours. Finally, we demonstrate the flexibility of the model by extending it to incorporate multiple state variables that might affect the response strategy. Collapse

Topics: application programming interface online learning system Twitter innovation management service quality

Methods: longitudinal research time series analysis generalized autoregressive conditional heteroskedasticity model natural language processing autoregressive moving average model

Theories: co-evolution theory

White knight in dark days? Supply chain finance firms, blockchain, and the COVID-19 pandemic

2022 | Information & Management | Citations: 0

Authors: Paul, Samit; Adhikari, Arnab; Bose, Indranil

Abstract: We investigate the impact of the announcement of the COVID-19 pandemic on the ma ... Expand

Abstract: We investigate the impact of the announcement of the COVID-19 pandemic on the market value and trading volume of supply chain finance (SCF) firms. Using an event study, we observe a significant valuation loss and higher trading volume of SCF firms. However, blockchain-enabled SCF firms are protected from such valuation loss and volatility in trading. We find that higher research and development (R&D) and capital expenditures by firms prevent the loss. Moreover, the firm value of blockchain-enabled SCF firms is impacted by their mem­ bership in a blockchain consortium and progress in blockchain implementation. Investors’ confidence in blockchain reduces the market uncertainty. Collapse

Topics: blockchain pandemic research and development supply chain management price management

Methods: longitudinal research event study regression analysis method cross sectional research Student's t-test

Theories: lemon market theory

Developing a Composite Measure to Represent Information Flows in Networks: Evidence from a Stock Market

2022 | Information Systems Research | Citations: 2

Authors: Shangguan, Wuyue (Phoebe); Leung, Alvin Chung Man; Agarwal, Ashish; Konana, Prabhudev; Chen, Xi

Abstract: There is increasing interest in information systems research to model informatio ... Expand

Abstract: There is increasing interest in information systems research to model information flows from different sources (e.g., social media, news) associated with a network of assets (e.g., stocks, products) and to study the economic impact of such information flows. This paper employs a design science approach and proposes a new composite metric, eigen attention centrality (EAC), as a proxy for information flows associated with a node that considers both attention to a node and coattention with other nodes in a network. We apply the EAC metric in the context of financial market where nodes are individual stocks and edges are based on coattention relationships among stocks. Composite information from different channels is used to measure attention and coattention. To evaluate the effectiveness of the EAC metric on predicting outcomes, we conduct an in-depth performance evaluation of the EAC metric by (1) using multiple linear and nonlinear prediction methods and (2) comparing EAC with a benchmark model without EAC and models with a set of alternative network metrics. Our analysis shows that EAC significantly outperforms other measures in predicting the direction and magnitude of abnormal returns of stocks. Besides, our EAC specification has better predictive performance than alternative specifications, and EAC outperforms direct attention in predicting abnormal returns. Using the EAC metric, we derive a stock portfolio and develop a trading strategy that provides significant and positive excess returns. Lastly, we find that composite information has significantly better predictive performance than separate information sources, and such superior performance owes to information from social media instead of traditional media. Collapse

Topics: social media evaluation criteria electronic trading database system accounting

Methods: machine learning design science longitudinal research autoregressive conditional heteroscedasticity model random forest classification

Quantifying the impacts of online fake news on the equity value of social media platforms – Evidence from Twitter

2022 | International Journal of Information Management | Citations: 0

Authors: Velichety, Srikar; Shrivastava, Utkarsh

Abstract: Online Fake News characterized by falsehood and ambiguity is significantly shaki ... Expand

Abstract: Online Fake News characterized by falsehood and ambiguity is significantly shaking up various aspects of social, economic, and political life across the globe. In addition, it can also be detrimental to the existence of social media platforms. In this research, by synthesizing the prior literature on negativity bias in online settings, reasons for platform failure and the characteristics of social media platforms, we explain the mechanisms through which online fake news impacts the equity value of these platforms. We also develop and implement a two-stage Bayesian Vector Autoregression technique to test these mechanisms using a dataset from Twitter. Our results show that falsehood results in an equity value loss of approximately 2.11 Million USD over a ten-day period while a mere 67.17 Million falsehood tweets can interact with ambiguity to produce a loss of 10 Million USD. We also find that ambiguity helps mitigate the negative impact of fake news which we attribute to the fact that users converse and disambiguate news that arrives on social media platforms. Our research has theoretical and practical implications for the impact of fake news on these platforms and their valuations. Collapse

Topics: fake news Twitter social media user-generated content misinformation

Methods: longitudinal research vector autoregression time series analysis descriptive statistic Monte Carlo simulation

Theories: elaboration likelihood model

Bitcoin price forecasting: A perspective of underlying blockchain transactions

2021 | Decision Support Systems | Citations: 7

Authors: Guo, Haizhou; Zhang, Dian; Liu, Siyuan; Wang, Lei; Ding, Ye

Abstract: Cryptocurrency price forecasting plays an important role in financial markets. T ... Expand

Abstract: Cryptocurrency price forecasting plays an important role in financial markets. Traditional approaches face two challenges: (1) it is difficult to ascertain the influential factors related to price forecasting; and (2) due to the 24/ 7 trading policy, cryptocurrencies’ prices face very large fluctuations, thus weakening the forecasting power of traditional models. To address these issues, we focus on Bitcoin and identify the influential factors related to its price forecasting from the perspective of underlying blockchain transactions. We then propose a price forecasting model WT-CATCN, which leverages Wavelet Transform (WT) and Casual Multi-Head Attention (CA) Temporal Convolutional Network (TCN), to forecast cryptocurrency prices. Our model can capture important positions of input sequences and model the correlations among different data features. Using real-world Bitcoin trading data, we test and compare WT-CATCN with other state-of-the-art price forecasting models. The experiment results show that our model improves the price forecasting performance by 25%. Collapse

Topics: Bitcoin cryptocurrency blockchain Google+ competitive advantage

Methods: experiment longitudinal research autoregressive integrated moving average computational algorithm deep learning

First, Do No Harm: Predictive Analytics to Reduce In-Hospital Adverse Events

2021 | Journal of Management Information Systems | Citations: 0

Authors: Lin, Yu-Kai; Fang, Xiao

Abstract: Inadequate patient safety is a serious issue in current medical practice. Medica ... Expand

Abstract: Inadequate patient safety is a serious issue in current medical practice. Medical errors cause adverse events (AEs) for patients and lead to premature deaths, unintended complications, prolonged hospital stays, and higher medical costs. Although the importance of AE prediction and prevention is well recognized in the information systems literature, there is a dearth of research on modeling and predicting AEs caused by medical errors. Following the design science research paradigm, this study describes the search, design, and evaluation of a novel in-hospital AE prediction model, called Stochastic Autoregressions for Latent Trajectories (SALT). The proposed model uniquely integrates generalized linear mixed model with multitask learning and stochastic time-series processes. Results from our empirical evaluation show that SALT outperforms prior state-of-the-art techniques in predicting AEs during patients' hospital stays. Through a simulation, we further demonstrate significant cost savings potential when hospitals implement and integrate SALT in their inpatient care. This study contributes to the design science literature by formalizing the in-hospital AE prediction problem, on the one hand, and developing a novel graphical model to address the prediction problem, on the other. For healthcare practitioners and administrators, our predictive analytics approach unveils important insights to minimize AEs. Collapse

Topics: organizational value knowledge base anonymity health information system problem solving

Methods: machine learning longitudinal research feature engineering time series analysis experiment

Information Asymmetry on Cryptocurrency Trading: The Spillover Effect and Quality of Social Sentiment.

2021 | Americas Conference on Information Systems | Citations: 0

Authors: kim, kwansoo; DAIDJ, Nabyla

Abstract: This study examines whether social sentiment can influence information asymmetr ... Expand

Abstract: This study examines whether social sentiment can influence information asymmetry in cryptocurrency markets, and if so, in what way and its qualitative effect? Using a data set on social sentiment by crawling Twitter and trading information on an exchange in Korea. We empirically study the linkage between social sentiment and asymmetric information in two cryptocurrency trading settings. Our results highlight the differentiated impact of positive and negative sentiment variance on information asymmetry according to 1) the spillover effects and 2) the leverage effect of social news characterizing social sentiment. However, the quality of the social sentiment related information is less valuable. Our findings contribute to the growing IS literature on the social media linked to Fintech as well as to the study of verifiability in the cryptocurrency market. Collapse

Topics: cryptocurrency social media Twitter Bitcoin communication service infrastructure

Methods: autoregressive conditional heteroscedasticity model generalized autoregressive conditional heteroskedasticity model sentiment analysis longitudinal research time series analysis

Theories: lemon market theory

Electric Vehicle Charging Decisions using Only Market Trends with Persistence

2020 | HICSS | Citations: 0

Authors: Hammerstrom, Donald J; Pratt, Richard M

Abstract: Electric vehicle (EV) charging can take advantage of real-time electricity mark ... Expand

Abstract: Electric vehicle (EV) charging can take advantage of real-time electricity market price volatility. Presuming that an EV must be fully charged at a future target time, the EV should choose to charge using the lowest future electricity prices and thereby minimize electricity cost. Statistical methods must be used if forward prices are unavailable. In this case, historical prices and trends must be mined to anticipate which prices should be used to charge the EV. Price persistence, a tendency for electricity prices to inexplicably become and remain relatively high or low for extended durations, is particularly difficult to forecast and mitigate. This paper formulates and tests a pragmatic strategy for integrating conventional static statistical prices and the Bayesian propagation of price persistence from the current price to prices in the current and future hours. Simulations were conducted to test the cost effectiveness of charging strategy using real-time electricity prices. 1 Collapse

Topics: price management programming language website

Methods: simulation longitudinal research autoregressive integrated moving average autocorrelation analysis autoregressive conditional heteroscedasticity model

The Voice of the Customer: Managing Customer Care in Twitter

2020 | Information Systems Research | Citations: 6

Authors: Mousavi, Reza; Johar, Monica; Mookerjee, Vijay S.

Abstract: In recent years, managing customer sentiment—particularly on social media—has be ... Expand

Abstract: In recent years, managing customer sentiment—particularly on social media—has become crucial as more customers use social media to seek help from firms. Therefore, we strive to determine an optimal strategy to manage customer sentiment on social media sites such as Twitter. We also aim to identify factors and external events that can influence the effectiveness of customer care. To understand the antecedents of digital customer care, we model a diffusion process of customer sentiment over time. This diffusion process is influenced (or controlled) by the firm through the strategy employed to respond to customer tweets. We then use real data consisting of sentiments expressed by customers directed at Twitter’s service accounts of four major U.S. telecommunication-service providers (AT&T, Verizon, Sprint, and T-Mobile) to estimate the parameters in our analytical model and shed several insights into digital customer care in this industry. First, we find a clear separation among the firms in terms of digital customer care effectiveness. Second, we find that good customer care is not merely a matter of responding to customer tweets. Third, the quality of digital customer care that customers expect varies across firms: Customers of higher priced firms (e.g., Verizon and AT&T) expect better customer care. Fourth, seemingly unrelated events (such as signing an exclusive contract with a celebrity) can impact digital customer care. Our study has important implications for managers as it can help firms determine the optimal strategy to influence customer sentiment. Collapse

Topics: Twitter customer service application programming interface social media Apple iPhone

Methods: sentiment analysis longitudinal research stochastic model simulation generalized autoregressive conditional heteroskedasticity model

Longitudinal healthcare analytics for disease management: Empirical demonstration for low back pain

2020 | Decision Support Systems | Citations: 0

Authors: Mueller-Peltzer, Michael; Feuerriegel, Stefan; Molgaard Nielsen, Anne; Kongsted, Alice; Vach, Werner; Neumann, Dirk

Abstract: Clinician guidelines recommend health management to tailor the form of care to t ... Expand

Abstract: Clinician guidelines recommend health management to tailor the form of care to the expected course of diseases. Hence, in order to decide upon a suitable treatment plan, health professionals benefit from decision support, i.e., predictions about how a disease is to evolve. In clinical practice, such a prediction model requires interpretability. Interpretability, however, is often precluded by complex dynamic models that would be capable of capturing the intrapersonal variability of disease trajectories. Therefore, we develop a cross-sectional ARMA model that allows for inference of the expected course of symptoms. Distinct from traditional time series models, it generalizes to cross-sectional settings and thus patient cohorts (i.e., it is estimated to multiple instead of single disease trajectories). Our model is evaluated according to a longitudinal 52-week study involving 928 patients with low back pain. It achieves a favorable prediction performance while maintaining interpretability. In sum, we provide decision support by informing health professionals about whether symptoms will have the tendency to stabilize or continue to be severe. Collapse

Topics: decision support decision making healthcare data missing data personalization

Methods: cross sectional research longitudinal research time series analysis autoregressive moving average model generalized autoregressive conditional heteroskedasticity model